---
title: sensenova-u1.5
canonical_url: "https://www.modelscope.ai/studios/Iceberg-Yang/sensenova-u1.5"
md_url: "https://www.modelscope.ai/studios/Iceberg-Yang/sensenova-u1.5.md"
repository: Iceberg-Yang/sensenova-u1.5
chinese_name: "SenseNova U1.5"
last_updated: 2026-09-03
sdk_type: gradio
sdk_version: 6.2.0
downloads: 0
stars: 6
---

# sensenova-u1.5

> sensenova-u1.5 - An interactive demo by Iceberg-Yang on ModelScope. Unified image generation & editing with SenseNova/SenseNova-U1.5-8B-MoT (NEO-Unify).

Iceberg-Yang/sensenova-u1.5 is an interactive demo (Studio) on ModelScope. built with gradio 6.2.0. also known as 「SenseNova U1.5」.

- **Repository**: Iceberg-Yang/sensenova-u1.5
- **SDK**: gradio
- **SDK version**: 6.2.0
- **Downloads**: 0
- **Stars**: 6
- **Last updated**: 2026-09-03

Source: https://www.modelscope.ai/studios/Iceberg-Yang/sensenova-u1.5

---

# SenseNova-U1.5-8B-MoT 📊

Unified **image generation and editing** with
[`SenseNova/SenseNova-U1.5-8B-MoT`](https://modelscope.cn/models/SenseNova/SenseNova-U1.5-8B-MoT),
running on a dedicated xGPU.

SenseNova-U1.5-8B-MoT is a monolithic **any-to-any (NEO-Unify)** model that
unifies multimodal understanding, generation, and editing in one architecture (no separate
visual encoder / VAE). It renders complex, text-dense infographics (charts, posters, knowledge
illustrations) across English and Chinese, and edits existing images via
natural-language instructions: local text edits, content insert / remove / replace, global
style changes, and layout tweaks.

This Space exposes two tabs:

- **Generate** — text → infographic (`t2i_generate`).
- **Edit** — image + instruction → edited image (`it2i_generate`).

Generation and editing use the model's officially recommended settings:
`cfg_scale=4.0`, `img_cfg_scale=1.0`, `cfg_norm="global"`, `timestep_shift=3.0`, `num_steps=50`.

The `sensenova_u1` package is vendored locally to register the NEO-Unify model
architecture with `transformers`.